Improving the accuracy of self-reported height and weight in surveys: an experimental study

Background Many studies rely on self-reported height and weight. While a substantial body of literature exists on misreporting of height and weight, little exists on improving accuracy. The aim of this study was to determine, using an experimental design and a comparative approach, whether the accuracy of self-reported height and weight data can be increased by improving how these questions are asked in surveys, drawing on the relevant evidence from the psychology and survey research literatures. Methods Two surveys from two separate studies were used to test our hypotheses (Science Survey, n = 1,200; Eating Behaviours Survey, n = 200). Participants were randomly assigned to one of six conditions, four of which were designed to improve the accuracy of the self-reported height and weight data ("preamble"), and two of which served as the control conditions ( "no preamble"). Four hypotheses were tested: (H1) survey participants read a preamble prior to being asked their height and weight will report lower heights and higher weights than those not read a preamble; (H2) the impact of question-wording (i.e., preamble vs. no preamble) on self-reported weight will be greater for participants with higher BMIs; (H3) the impact of question-wording on height will be greater for older participants; (H4) either version of the weight question - standard or "weight-specific"-may result in participants reporting more accurate self-reported weight. One-way MANOVA was conducted to test Hypothesis 1; two-way analysis of variance were conducted to test Hypothesis 2; moderation analysis was used to test Hypothesis 3; independent samples t-test was conducted to test Hypothesis 4. Results None of the hypotheses was supported. Conclusions This paper provides an important starting point from which to inform further work exploring how question wording can improve self-reported measurement of height and weight. Future research should explore how question preambles may or may not operationalise hypothesised underlying mechanisms, the sensitivity or intrusiveness of height and weight questions, individual beliefs about one's height and weight, and survey context.